Detection of Falls with Smartphone Using Machine Learning Technique

As the population aging issue becomes more serious these days, fall detection of the elderly has been attracting a great deal of interests. A fall detection system includes data collection, data pre-processing, feature extraction, feature selection, and then activity classification. In this context the researchers have conducted studies on acceleration-based fall detection using external accelerometer or built-in sensors in smartphone. In this paper a novel approach for fall detection using machine learning technique is proposed, which employs a new pre-processing technique to remove noise from sensor data. It mainly consists of two processes: short-term smoothing to remove the short term vibration and long-term smoothing to smooth sensor readings captured in a longer time window. To detect falls, statistical models are proposed to extract the features. A public dataset, MobiFall, is used for performance evaluation, which contains the data of accelerometer and gyroscope with the orientation along each axis in the smartphone coordination system. With the selected features, the proposed scheme identifies falls from the activities of daily living with a high accuracy of up to 98.3%. Moreover, tFall dataset is also used to perform a cross verification of the proposed scheme.